InferenceBench

embeddings.retrieval.beir-mini

1 entry. Pareto frontier computed on throughput_tok_per_s (higher is better) vs. ttft_p50_ms (lower is better). Rows marked P are on the frontier.

1 of 1 matching
Model Engine Hardware Quant TTFT P50 (ms) TTFT P99 (ms) Throughput (tok/s) $/M tokens J/token Power avg (W) Power peak (W) WER mean J / audio s Envelope
BAAI/bge-large-en-v1.5 openai unknown 8x NVIDIA H100 80GB HBM3 fp32 JSON